Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3336 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5926. Min Range: -1.5926

Max Act: 1.5926. Min Act: -0.0000

Data Index: 383439 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 1.5926. Min Range: -1.5926

Max Act: 1.1064. Min Act: -0.0000

Data Index: 881470 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 1.5926. Min Range: -1.5926

Max Act: 1.0050. Min Act: -0.0000

Data Index: 399530 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1121891 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1264053 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1235103 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.7681. Min Act: -0.0000

Data Index: 568816 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1142176 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.7859. Min Act: -0.0000

Data Index: 389060 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1104078 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.7316. Min Act: -0.0000

Data Index: 21279 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1287037 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.6697. Min Act: -0.0000

Data Index: 655197 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.7064. Min Act: -0.0000

Data Index: 545777 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.6948. Min Act: -0.0000

Data Index: 935760 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1175926 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.6821. Min Act: -0.0000

Data Index: 417931 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.6328. Min Act: -0.0000

Data Index: 80740 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1228523 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 1.5926. Min Range: -1.5926

Max Act: 0.6713. Min Act: -0.0000

Data Index: 949068 (C4 (Web Text))

Max Activating Token Index: 918